Browse / Computers
Computational Learning Theory 9783540438366

Computational Learning Theory

15th Annual Conference on Computational Learning Theory, COLT 2002, Sydney, Australia, July 2002, Pr...

ISBN-10: 354043836X
ISBN-13: 9783540438366
PUBLISHER: Springer
Also available at Amazon.com
Note: Not guaranteed to come with supplemental materials (access codes, CDs, DVDs)
Product Description: ThisvolumecontainspaperspresentedattheFifteenthAnnualConferenceon ComputationalLearningTheory(COLT2002)heldonthemaincampusofthe UniversityofNewSouthWalesinSydney,AustraliafromJuly8to10,2002. Naturally,thesearepapersinthe?eldofcomputationallearningtheory,a- search?elddevotedtostudyingthedesignandanalysisofalgorithmsformaking predictionsaboutthefuturebasedonpastexperiences,withanemphasisonr- orousmathematicalanalysis. COLT2002wasco-locatedwiththeNineteenthInternationalConferenceon MachineLearning(ICML2002)andwiththeTwelfthInternationalConference onInductiveLogicProgramming(ILP2002). NotethatCOLT2002wasthe?rstconferencetotakeplaceafterthefull mergeroftheAnnualConferenceonComputationalLearningTheorywiththe EuropeanConferenceonComputationalLearningTheory. (In2001ajointc- ferenceconsistingofthe5thEuropeanConferenceonComputationalLearning Theoryandthe14thAnnualConferenceonComputationalLearningTheory washeld;thelastindependentEuropeanConferenceonComputationalLea- ingTheorywasheldin1999. ) ThetechnicalprogramofCOLT2002contained26papersselectedfrom 55submissions. Inaddition,ChristosPapadimitriou(UniversityofCaliforniaat Berkeley)wasinvitedtogiveakeynotelectureandtocontributeanabstractof hislecturetotheseproceedings. TheMarkFulkAwardispresentedannuallyforthebestpapercoauthored byastudent. Thisyear''sawardwaswonbySandraZillesforthepaper"Merging UniformInductiveLearners. " April2002 JyrkiKivinen RobertH. Sloan Thanks and Acknowledgments Wegratefullythankalltheindividualsandorganizationsresponsibleforthe successoftheconference. ProgramCommittee Weespeciallywanttothanktheprogramcommittee:DanaAngluin(Yale), JavedAslam(Dartmouth),PeterBartlett(BIOwulfTechnologies),ShaiBen- David(Technion),JohnCase(Univ. ofDelaware),PeterGru¨nwald(CWI),Ralf Herbrich(MicrosoftResearch),MarkHerbster(UniversityCollegeLondon), G´aborLugosi(PompeuFabraUniversity),RonMeir(Technion),ShaharMend- son(AustralianNationalUniv. ),MichaelSchmitt(Ruhr-Universit¨atBochum), RoccoServedio(Harvard),andSantoshVempala(MIT). WealsoacknowledgethecreatorsoftheCyberChairsoftwareformakinga softwarepackagethathelpedthecommitteedoitswork. Local Arrangements, Co-located Conferences Support SpecialthanksgotoourconferencechairArunSharmaandlocalarrangements chairEricMartin(bothatUniv. ofNewSouthWales)forsettingupCOLT2002 inSydney. RochelleMcDonaldandSueLewisprovidedadministrativesupport. ClaudeSammutinhisroleasconferencechairofICMLandprogramco-chair ofILPensuredsmoothcoordinationwiththetwoco-locatedconferences. COLT Community ForkeepingtheCOLTseriesgoing,wethanktheCOLTsteeringcommittee, andespeciallyChairJohnShawe-TaylorandTreasurerJohnCaseforalltheir hardwork. WealsothankStephenKwekformaintainingtheCOLTwebsiteat http://www. learningtheory. org. Sponsoring Institution SchoolofComputerScienceandEngineering,UniversityofNewSouthWales, Australia VIII Thanks and Acknowledgments Referees PeterAuer LisaHellerstein AlainPajor AndrewBarto DanielHerrmann GunnarR¨atsch StephaneBoucheron ColindelaHiguera RobertSchapire OlivierBousquet SeanHolden JohnShawe-Taylor Nicol`oCesa-Bianchi MarcusHutter TakeshiShinohara TapioElomaa SanjayJain DavidShmoys RanEl-Yaniv YuriKalnishkan YoramSinger AllanErskine MakotoKanazawa CarlSmith HenningFernau SatoshiKobayashi FrankStephan J¨urgenForster VladimirKoltchinskii Gy¨orgyTur´an DeanFoster MattiKa¨ ¨ariai ¨nen PaulVitan ´yi ClaudioGentile WeeSunLee ManfredWarmuth JudyGoldsmith ShieMannor JonA. Wellner ThoreGraepel RyanO''Donnell RobertC. Williamson Table of Contents Statistical Learning Theory AgnosticLearningNonconvexFunctionClasses. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 Shahar Mendelson andRobertC. Williamson Entropy,CombinatorialDimensionsandRandomAverages. . . . . . . . . . . . . . . . . 14 Shahar Mendelson andRoman Vershynin GeometricParametersofKernelMachines. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 Shahar Mendelson LocalizedRademacherComplexities. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44 PeterL. Bartlett,Olivier Bousquet,and Shahar Mendelson SomeLocalMeasuresofComplexityofConvexHulls andGeneralizationBounds . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59 Olivier Bousquet,Vladimir Koltchinskii, and DmitriyPanchenko OnlineLearning PathKernelsandMultiplicativeUpdates. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 74 Eiji Takimoto andManfred K. Warmuth PredictiveComplexityandInformation. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 90 Michael V. Vyugin andVladimir V. V''yugin MixabilityandtheExistenceofWeakComplexities. . . . . . . . . . . . . . . . . . . . . . . 105 YuriKalnishkan andMichael V. Vyugin ASecond-OrderPerceptronAlgorithm. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 121 Nicolo ` Cesa-Bianchi, AlexConconi, and Claudio Gentile TrackingLinear-ThresholdConceptswithWinnow . . . . . . . . . . . . . . . . . . . . . . . . 138 Chris Mesterharm Inductive Inference LearningTreeLanguagesfromText. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 153 HenningFernau PolynomialTimeInductiveInferenceofOrderedTreePatterns withInternalStructuredVariablesfromPositiveData . . . . . . . . . . . . . . . . . . . . 169 YusukeSuzuki,RyutaAkanuma,Takayoshi Shoudai, TetsuhiroMiyahara, andTomoyuki Uchida X Table of Contents InferringDeterministicLinearLanguages. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 185 Colin dela HigueraandJoseOncina MergingUniformInductiveLearners. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 201 SandraZilles TheSpeedPrior:ANewSimplicityMeasure YieldingNear-OptimalComputablePredictions. . . . . . . . . . . . . . . . . . . . . . . . . . . 216 J¨ urgenSchmidhuber PAC Learning NewLowerBoundsforStatisticalQueryLearning. . . . . . . . . . . . . . . . . . . . . . . . 229 KeYang ExploringLearnabilitybetweenExactandPAC. . . . . . . . . . . . . . . . . . . . . . . . . . . 244 Nader H. Bshouty, Je?reyC. Jackson, andChristino Tamon PACBoundsforMulti-armedBanditandMarkovDecisionProcesses. . . . .

Additional Details


PUBLICATION DATE:
CATEGORY: Computers
Star

21 Day Unconditional Guarantee

any book, any reason

Rent This Book Now:

Price guaranteed for 45 minutes
Due May 15 $64.06
130 days (due Jul 3) $70.82
85 days (due May 19) $64.44
55 days (due Apr 19) $61.61
Select Your Own Date
--

Buy this book used:

$80.82

List Price: $119.00
Your Savings:
Total Price:
 

REVIEWS for Computational Learning Theory


Select a star rating

FAQ'S

1. How do textbook rentals work?
It’s simple. Begin by searching for your textbook by ISBN (10 or 13-digit number that can be found on the back cover of each book), title, author or keyword. Next select how long you would like to rent the book then add it to your cart. Repeat for each book you’re looking for. After completing the order we’ll ship them to you and you’ll also receive a prepaid mailer. Return your books in the mailer by your rental due date.
2. Is renting a textbook better than purchasing it?
We offer both! You can buy or rent the book through Campus Book Rentals. It’s up to you to decide which option best meets your educational needs.
3. How do I track my order?
Login to your account here, you’ll see your current rentals listed textbook rentals listed with a yellow box that says “track”. Click the box to view the tracking number. *Not all books will have a tracking number since they may be sent from one of our partners. Tracking numbers will be updated as they become available.
4. How do I return my books?
When you rent textbooks from Campus Book Rentals you’ll receive a prepaid mailer. When it’s nearing your due date you’ll place your books inside the mailer and take it to the nearest USPS drop box or Post Office. If you don’t receive a mailer you can print a return label from your account. Return shipping is prepaid so please use either of the two methods to ensure they arrive at the correct facility.
5. Can I write or highlight in my book?
Of course! Just remember that future students will rent the same book after you, so please be respectful.
6. How much money can renting my books save?
It depends on the book. Generally renting textbooks can save you up to 80% compared to a new textbook.
7. Are Campus Book Rentals’ books the same as my bookstore’s?
Yes! We only ship US edition textbooks, which are the same as your campus bookstore.
8. Do access codes or other supplements come with a textbook rental?
One time use access codes and other supplemental materials are NOT included with rental books and must be purchased separately.
9. What if I don’t return my rental?
If your book rental is not returned by the due date, your credit card will be charged a non-return fee, equal to the replacement value for the book.
10. Can I purchase my book after I rent it?
Certainty! You’re only charged the difference between what you already paid and the value of the book at the time you initially rented. Login to your account and choose to purchase your book and it’ll walk you through the checkout process.

Textbook Rentals

We know that textbook rentals are the best way currently to distribute high quality textbooks, and we want to have you on board! Join over a million students that have saved money by renting! Not only is it better for you, but when you return it that book can go on to help even more students access affordable education. We're confident we offer the best value in rentals, but if you're not a believer you can always return your book for a no questions asked refund within 21 days.

Why Choose Us?

1. Campus Book Rentals pioneered the idea of textbook rentals, making prices significantly cheaper for every student while still maintaining the highest quality. We've been at it since 2007 and the entire industry has had to adapt to keep up.

2. Though keeping prices low has always been the goal, we can boast an excellent support team that has helped thousands of students get the best value for their education. Chat with them at 855-200-0021 or use our chat box.

3. We practice what we preach. We routinely read our own textbooks to further our own education while at work. We know that only with a well-educated team of individuals can we continue to change the industry for the better.

Make A Difference

At Campus Book Rentals our company is guided by a single question, "How are we making education more affordable?" We know that getting a college education is quickly becoming a rite of passage for students and is becoming more important every year. In order to make education more attainable for the 99%, we started renting textbooks so students could avoid high purchase prices and buyback programs. We know it's a better way, and we're going to show everyone how to make a college education affordable again.